Outcome-Driven AI Orchestration Framework (ODAO): An Intent-Centric and Model-Agnostic Architecture for Enterprise AI Systems

Authors

  • Vijayalakshmi Narasimhan

Keywords:

Agentic Workflow, Enterprise AI Architecture, Intent Modeling, Model-Agnostic Orchestration, Outcome Optimization

Abstract

Enterprise adoption of artificial intelligence (AI) systems powered by large language models (LLMs), retrieval-augmented generation (RAG), and multi-agent architectures has outpaced the development of orchestration frameworks capable of governing them at scale. Prevailing approaches remain model-centric, pipeline-static, and structurally disconnected from measurable business outcomes — limitations that compound as enterprise AI programs expand across multiple products, teams, and deployment environments. This paper introduces the Outcome-Driven AI Orchestration Framework (ODAO), a novel model-agnostic architecture that redefines enterprise AI system design around user intent and outcome optimization. ODAO formalizes five integrated layers: use case-to-intent modeling, intent-to-skill decomposition, agent composition, dynamic workflow execution, and outcome-driven feedback. The framework is evaluated over a ten-week enterprise codebase intelligence deployment involving 156 active users, demonstrating a 41% improvement in workflow adaptability score, a 36% increase in skill reuse ratio, a 29% improvement in outcome achievement rate, and stable latency compliance at 93.1%, compared to a static pipeline baseline. The primary contributions are a formal intent representation model, an atomic skill taxonomy spanning five capability categories, a dynamic agent workflow composition model, an outcome evaluation mechanism distinguishing outputs from outcomes at three organizational granularity levels, and a configuration-space optimization feedback loop. Together, these contributions establish ODAO as a production-ready, governance-aligned orchestration architecture for enterprise AI programs operating at scale.

Downloads

Download data is not yet available.

References

T. B. Brown et al., "Language models are few-shot learners," arxiv > cs > arXiv:2005.14165, vol. 33, 2020, pp. 1877–1901. [Online]. Available: https://arxiv.org/abs/2005.14165

P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," in Proc. Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2021, pp. 9459–9474. [Online]. Available: https://arxiv.org/abs/2005.11401

T. Guo et al., "Large language model based multi-agents: A survey of progress and challenges," in Proc. 33rd Int. Joint Conf. Artificial Intelligence (IJCAI), 2024. [Online]. Available: https://dl.acm.org/doi/10.24963/ijcai.2024/890

T. Schick et al., "Toolformer: Language models can teach themselves to use tools," arXiv preprint arXiv:2302.04761, 2023. [Online]. Available: https://arxiv.org/abs/2302.04761

A. Paleyes et al., "Challenges in deploying machine learning: A survey of case studies," ACM Computing Surveys, vol. 55, no. 6, art. 114, Dec. 2022. [Online]. Available: https://dl.acm.org/doi/10.1145/3533378

K. Ahmad et al., "Requirements engineering for artificial intelligence systems: A systematic mapping study," Information and Software Technology, vol. 158, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S0950584923000307

S. Yao et al., "ReAct: Synergizing reasoning and acting in language models," in Proc. 11th Int. Conf. Learning Representations (ICLR), 2023. [Online]. Available: https://arxiv.org/abs/2210.03629

S. Hong et al., "MetaGPT: Meta programming for a multi-agent collaborative framework," in Proc. 12th Int. Conf. Learning Representations (ICLR), 2024. [Online]. Available: https://arxiv.org/abs/2308.00352

L. Wang et al., "A survey on large language model based autonomous agents," Frontiers of Computer Science, vol. 18, art. 186345, 2024. [Online]. Available: https://link.springer.com/article/10.1007/s11704-024-40231-1

Z. Xi et al., "The rise and potential of large language model based agents: A survey," arXiv preprint arXiv:2309.07864, 2023. [Online]. Available: https://arxiv.org/abs/2309.07864

Z. Liu et al., "A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration," arXiv preprint arXiv:2310.02170, 2024. [Online]. Available: https://arxiv.org/abs/2310.02170

C. Qian et al., "ChatDev: Communicative agents for software development," Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024. [Online]. Available: https://aclanthology.org/2024.acl-long.810/

N. Shinn et al., "Reflexion: Language agents with verbal reinforcement learning," in Proc. 37th Conf. Neural Information Processing Systems (NeurIPS), 2023. [Online]. Available: https://arxiv.org/abs/2303.11366

J. Wei et al., "Chain-of-thought prompting elicits reasoning in large language models," in Proc. Advances in Neural Information Processing Systems (NeurIPS), vol. 35, 2022. [Online]. Available: https://arxiv.org/abs/2201.11903

Y. Qin et al., "Tool learning with foundation models," ACM Computing Surveys, vol. 57, 2024. [Online]. Available: https://dl.acm.org/doi/10.1145/3704435

P. Liang et al., "Holistic evaluation of language models," arXiv preprint arXiv:2211.09110, 2023. [Online]. Available: https://arxiv.org/abs/2211.09110

L. Zheng et al., "Judging LLM-as-a-judge with MT-Bench and Chatbot Arena," in Proc. 37th Conf. Neural Information Processing Systems (NeurIPS), 2023. [Online]. Available: https://arxiv.org/abs/2306.05685

X. Deng et al., "Mind2Web: Towards a generalist agent for the web," in Proc. 37th Conf. Neural Information Processing Systems (NeurIPS), 2023. [Online]. Available: https://arxiv.org/abs/2306.06070

National Institute of Standards and Technology, "Artificial intelligence risk management framework (AI RMF 1.0)," NIST AI 100-1, Jan. 2023. [Online]. Available: https://nvlpubs.nist.gov/nistpubs/ai/nist.ai.100-1.pdf

D. Sculley et al., "Hidden technical debt in machine learning systems," Advances in Neural Information Processing Systems, vol. 28, 2015. [Online]. Available: https://www.researchgate.net/publication/319769912_Hidden_Technical_Debt_in_Machine_Learning_Systems

S. Amershi et al., "Software engineering for machine learning: A case study," ICSE-SEIP '19: Proceedings of the 41st International Conference on Software Engineering: Software Engineering in Practice, 2019, pp. 291–300. [Online]. Available: https://dl.acm.org/doi/10.1109/icse-seip.2019.00042

Downloads

Published

20.06.2026

How to Cite

Vijayalakshmi Narasimhan. (2026). Outcome-Driven AI Orchestration Framework (ODAO): An Intent-Centric and Model-Agnostic Architecture for Enterprise AI Systems. International Journal of Intelligent Systems and Applications in Engineering, 14(1s), 1597–1609. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/8391

Issue

Vol. 14 No. 1s (2026)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.